updates

Backend/venv/lib/python3.12/site-packages/nltk/app/__init__.py

@@ -0,0 +1,47 @@
+# Natural Language Toolkit: Applications package
+#
+# Copyright (C) 2001-2025 NLTK Project
+# Author: Edward Loper <edloper@gmail.com>
+#         Steven Bird <stevenbird1@gmail.com>
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+
+"""
+Interactive NLTK Applications:
+
+chartparser:  Chart Parser
+chunkparser:  Regular-Expression Chunk Parser
+collocations: Find collocations in text
+concordance:  Part-of-speech concordancer
+nemo:         Finding (and Replacing) Nemo regular expression tool
+rdparser:     Recursive Descent Parser
+srparser:     Shift-Reduce Parser
+wordnet:      WordNet Browser
+"""
+
+
+# Import Tkinter-based modules if Tkinter is installed
+try:
+    import tkinter
+except ImportError:
+    import warnings
+
+    warnings.warn("nltk.app package not loaded (please install Tkinter library).")
+else:
+    from nltk.app.chartparser_app import app as chartparser
+    from nltk.app.chunkparser_app import app as chunkparser
+    from nltk.app.collocations_app import app as collocations
+    from nltk.app.concordance_app import app as concordance
+    from nltk.app.nemo_app import app as nemo
+    from nltk.app.rdparser_app import app as rdparser
+    from nltk.app.srparser_app import app as srparser
+    from nltk.app.wordnet_app import app as wordnet
+
+    try:
+        from matplotlib import pylab
+    except ImportError:
+        import warnings
+
+        warnings.warn("nltk.app.wordfreq not loaded (requires the matplotlib library).")
+    else:
+        from nltk.app.wordfreq_app import app as wordfreq

Backend/venv/lib/python3.12/site-packages/nltk/app/collocations_app.py

@@ -0,0 +1,438 @@
+# Natural Language Toolkit: Collocations Application
+# Much of the GUI code is imported from concordance.py; We intend to merge these tools together
+# Copyright (C) 2001-2025 NLTK Project
+# Author: Sumukh Ghodke <sghodke@csse.unimelb.edu.au>
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+#
+
+
+import queue as q
+import threading
+from tkinter import (
+    END,
+    LEFT,
+    SUNKEN,
+    Button,
+    Frame,
+    IntVar,
+    Label,
+    Menu,
+    OptionMenu,
+    Scrollbar,
+    StringVar,
+    Text,
+    Tk,
+)
+from tkinter.font import Font
+
+from nltk.corpus import (
+    alpino,
+    brown,
+    cess_cat,
+    cess_esp,
+    floresta,
+    indian,
+    mac_morpho,
+    machado,
+    nps_chat,
+    sinica_treebank,
+    treebank,
+)
+from nltk.probability import FreqDist
+from nltk.util import in_idle
+
+CORPUS_LOADED_EVENT = "<<CL_EVENT>>"
+ERROR_LOADING_CORPUS_EVENT = "<<ELC_EVENT>>"
+POLL_INTERVAL = 100
+
+_DEFAULT = "English: Brown Corpus (Humor)"
+_CORPORA = {
+    "Catalan: CESS-CAT Corpus": lambda: cess_cat.words(),
+    "English: Brown Corpus": lambda: brown.words(),
+    "English: Brown Corpus (Press)": lambda: brown.words(
+        categories=["news", "editorial", "reviews"]
+    ),
+    "English: Brown Corpus (Religion)": lambda: brown.words(categories="religion"),
+    "English: Brown Corpus (Learned)": lambda: brown.words(categories="learned"),
+    "English: Brown Corpus (Science Fiction)": lambda: brown.words(
+        categories="science_fiction"
+    ),
+    "English: Brown Corpus (Romance)": lambda: brown.words(categories="romance"),
+    "English: Brown Corpus (Humor)": lambda: brown.words(categories="humor"),
+    "English: NPS Chat Corpus": lambda: nps_chat.words(),
+    "English: Wall Street Journal Corpus": lambda: treebank.words(),
+    "Chinese: Sinica Corpus": lambda: sinica_treebank.words(),
+    "Dutch: Alpino Corpus": lambda: alpino.words(),
+    "Hindi: Indian Languages Corpus": lambda: indian.words(files="hindi.pos"),
+    "Portuguese: Floresta Corpus (Portugal)": lambda: floresta.words(),
+    "Portuguese: MAC-MORPHO Corpus (Brazil)": lambda: mac_morpho.words(),
+    "Portuguese: Machado Corpus (Brazil)": lambda: machado.words(),
+    "Spanish: CESS-ESP Corpus": lambda: cess_esp.words(),
+}
+
+
+class CollocationsView:
+    _BACKGROUND_COLOUR = "#FFF"  # white
+
+    def __init__(self):
+        self.queue = q.Queue()
+        self.model = CollocationsModel(self.queue)
+        self.top = Tk()
+        self._init_top(self.top)
+        self._init_menubar()
+        self._init_widgets(self.top)
+        self.load_corpus(self.model.DEFAULT_CORPUS)
+        self.after = self.top.after(POLL_INTERVAL, self._poll)
+
+    def _init_top(self, top):
+        top.geometry("550x650+50+50")
+        top.title("NLTK Collocations List")
+        top.bind("<Control-q>", self.destroy)
+        top.protocol("WM_DELETE_WINDOW", self.destroy)
+        top.minsize(550, 650)
+
+    def _init_widgets(self, parent):
+        self.main_frame = Frame(
+            parent, dict(background=self._BACKGROUND_COLOUR, padx=1, pady=1, border=1)
+        )
+        self._init_corpus_select(self.main_frame)
+        self._init_results_box(self.main_frame)
+        self._init_paging(self.main_frame)
+        self._init_status(self.main_frame)
+        self.main_frame.pack(fill="both", expand=True)
+
+    def _init_corpus_select(self, parent):
+        innerframe = Frame(parent, background=self._BACKGROUND_COLOUR)
+        self.var = StringVar(innerframe)
+        self.var.set(self.model.DEFAULT_CORPUS)
+        Label(
+            innerframe,
+            justify=LEFT,
+            text=" Corpus: ",
+            background=self._BACKGROUND_COLOUR,
+            padx=2,
+            pady=1,
+            border=0,
+        ).pack(side="left")
+
+        other_corpora = list(self.model.CORPORA.keys()).remove(
+            self.model.DEFAULT_CORPUS
+        )
+        om = OptionMenu(
+            innerframe,
+            self.var,
+            self.model.DEFAULT_CORPUS,
+            command=self.corpus_selected,
+            *self.model.non_default_corpora()
+        )
+        om["borderwidth"] = 0
+        om["highlightthickness"] = 1
+        om.pack(side="left")
+        innerframe.pack(side="top", fill="x", anchor="n")
+
+    def _init_status(self, parent):
+        self.status = Label(
+            parent,
+            justify=LEFT,
+            relief=SUNKEN,
+            background=self._BACKGROUND_COLOUR,
+            border=0,
+            padx=1,
+            pady=0,
+        )
+        self.status.pack(side="top", anchor="sw")
+
+    def _init_menubar(self):
+        self._result_size = IntVar(self.top)
+        menubar = Menu(self.top)
+
+        filemenu = Menu(menubar, tearoff=0, borderwidth=0)
+        filemenu.add_command(
+            label="Exit", underline=1, command=self.destroy, accelerator="Ctrl-q"
+        )
+        menubar.add_cascade(label="File", underline=0, menu=filemenu)
+
+        editmenu = Menu(menubar, tearoff=0)
+        rescntmenu = Menu(editmenu, tearoff=0)
+        rescntmenu.add_radiobutton(
+            label="20",
+            variable=self._result_size,
+            underline=0,
+            value=20,
+            command=self.set_result_size,
+        )
+        rescntmenu.add_radiobutton(
+            label="50",
+            variable=self._result_size,
+            underline=0,
+            value=50,
+            command=self.set_result_size,
+        )
+        rescntmenu.add_radiobutton(
+            label="100",
+            variable=self._result_size,
+            underline=0,
+            value=100,
+            command=self.set_result_size,
+        )
+        rescntmenu.invoke(1)
+        editmenu.add_cascade(label="Result Count", underline=0, menu=rescntmenu)
+
+        menubar.add_cascade(label="Edit", underline=0, menu=editmenu)
+        self.top.config(menu=menubar)
+
+    def set_result_size(self, **kwargs):
+        self.model.result_count = self._result_size.get()
+
+    def _init_results_box(self, parent):
+        innerframe = Frame(parent)
+        i1 = Frame(innerframe)
+        i2 = Frame(innerframe)
+        vscrollbar = Scrollbar(i1, borderwidth=1)
+        hscrollbar = Scrollbar(i2, borderwidth=1, orient="horiz")
+        self.results_box = Text(
+            i1,
+            font=Font(family="courier", size="16"),
+            state="disabled",
+            borderwidth=1,
+            yscrollcommand=vscrollbar.set,
+            xscrollcommand=hscrollbar.set,
+            wrap="none",
+            width="40",
+            height="20",
+            exportselection=1,
+        )
+        self.results_box.pack(side="left", fill="both", expand=True)
+        vscrollbar.pack(side="left", fill="y", anchor="e")
+        vscrollbar.config(command=self.results_box.yview)
+        hscrollbar.pack(side="left", fill="x", expand=True, anchor="w")
+        hscrollbar.config(command=self.results_box.xview)
+        # there is no other way of avoiding the overlap of scrollbars while using pack layout manager!!!
+        Label(i2, text="   ", background=self._BACKGROUND_COLOUR).pack(
+            side="left", anchor="e"
+        )
+        i1.pack(side="top", fill="both", expand=True, anchor="n")
+        i2.pack(side="bottom", fill="x", anchor="s")
+        innerframe.pack(side="top", fill="both", expand=True)
+
+    def _init_paging(self, parent):
+        innerframe = Frame(parent, background=self._BACKGROUND_COLOUR)
+        self.prev = prev = Button(
+            innerframe,
+            text="Previous",
+            command=self.previous,
+            width="10",
+            borderwidth=1,
+            highlightthickness=1,
+            state="disabled",
+        )
+        prev.pack(side="left", anchor="center")
+        self.next = next = Button(
+            innerframe,
+            text="Next",
+            command=self.__next__,
+            width="10",
+            borderwidth=1,
+            highlightthickness=1,
+            state="disabled",
+        )
+        next.pack(side="right", anchor="center")
+        innerframe.pack(side="top", fill="y")
+        self.reset_current_page()
+
+    def reset_current_page(self):
+        self.current_page = -1
+
+    def _poll(self):
+        try:
+            event = self.queue.get(block=False)
+        except q.Empty:
+            pass
+        else:
+            if event == CORPUS_LOADED_EVENT:
+                self.handle_corpus_loaded(event)
+            elif event == ERROR_LOADING_CORPUS_EVENT:
+                self.handle_error_loading_corpus(event)
+        self.after = self.top.after(POLL_INTERVAL, self._poll)
+
+    def handle_error_loading_corpus(self, event):
+        self.status["text"] = "Error in loading " + self.var.get()
+        self.unfreeze_editable()
+        self.clear_results_box()
+        self.freeze_editable()
+        self.reset_current_page()
+
+    def handle_corpus_loaded(self, event):
+        self.status["text"] = self.var.get() + " is loaded"
+        self.unfreeze_editable()
+        self.clear_results_box()
+        self.reset_current_page()
+        # self.next()
+        collocations = self.model.next(self.current_page + 1)
+        self.write_results(collocations)
+        self.current_page += 1
+
+    def corpus_selected(self, *args):
+        new_selection = self.var.get()
+        self.load_corpus(new_selection)
+
+    def previous(self):
+        self.freeze_editable()
+        collocations = self.model.prev(self.current_page - 1)
+        self.current_page = self.current_page - 1
+        self.clear_results_box()
+        self.write_results(collocations)
+        self.unfreeze_editable()
+
+    def __next__(self):
+        self.freeze_editable()
+        collocations = self.model.next(self.current_page + 1)
+        self.clear_results_box()
+        self.write_results(collocations)
+        self.current_page += 1
+        self.unfreeze_editable()
+
+    def load_corpus(self, selection):
+        if self.model.selected_corpus != selection:
+            self.status["text"] = "Loading " + selection + "..."
+            self.freeze_editable()
+            self.model.load_corpus(selection)
+
+    def freeze_editable(self):
+        self.prev["state"] = "disabled"
+        self.next["state"] = "disabled"
+
+    def clear_results_box(self):
+        self.results_box["state"] = "normal"
+        self.results_box.delete("1.0", END)
+        self.results_box["state"] = "disabled"
+
+    def fire_event(self, event):
+        # Firing an event so that rendering of widgets happen in the mainloop thread
+        self.top.event_generate(event, when="tail")
+
+    def destroy(self, *e):
+        if self.top is None:
+            return
+        self.top.after_cancel(self.after)
+        self.top.destroy()
+        self.top = None
+
+    def mainloop(self, *args, **kwargs):
+        if in_idle():
+            return
+        self.top.mainloop(*args, **kwargs)
+
+    def unfreeze_editable(self):
+        self.set_paging_button_states()
+
+    def set_paging_button_states(self):
+        if self.current_page == -1 or self.current_page == 0:
+            self.prev["state"] = "disabled"
+        else:
+            self.prev["state"] = "normal"
+        if self.model.is_last_page(self.current_page):
+            self.next["state"] = "disabled"
+        else:
+            self.next["state"] = "normal"
+
+    def write_results(self, results):
+        self.results_box["state"] = "normal"
+        row = 1
+        for each in results:
+            self.results_box.insert(str(row) + ".0", each[0] + " " + each[1] + "\n")
+            row += 1
+        self.results_box["state"] = "disabled"
+
+
+class CollocationsModel:
+    def __init__(self, queue):
+        self.result_count = None
+        self.selected_corpus = None
+        self.collocations = None
+        self.CORPORA = _CORPORA
+        self.DEFAULT_CORPUS = _DEFAULT
+        self.queue = queue
+        self.reset_results()
+
+    def reset_results(self):
+        self.result_pages = []
+        self.results_returned = 0
+
+    def load_corpus(self, name):
+        self.selected_corpus = name
+        self.collocations = None
+        runner_thread = self.LoadCorpus(name, self)
+        runner_thread.start()
+        self.reset_results()
+
+    def non_default_corpora(self):
+        copy = []
+        copy.extend(list(self.CORPORA.keys()))
+        copy.remove(self.DEFAULT_CORPUS)
+        copy.sort()
+        return copy
+
+    def is_last_page(self, number):
+        if number < len(self.result_pages):
+            return False
+        return self.results_returned + (
+            number - len(self.result_pages)
+        ) * self.result_count >= len(self.collocations)
+
+    def next(self, page):
+        if (len(self.result_pages) - 1) < page:
+            for i in range(page - (len(self.result_pages) - 1)):
+                self.result_pages.append(
+                    self.collocations[
+                        self.results_returned : self.results_returned
+                        + self.result_count
+                    ]
+                )
+                self.results_returned += self.result_count
+        return self.result_pages[page]
+
+    def prev(self, page):
+        if page == -1:
+            return []
+        return self.result_pages[page]
+
+    class LoadCorpus(threading.Thread):
+        def __init__(self, name, model):
+            threading.Thread.__init__(self)
+            self.model, self.name = model, name
+
+        def run(self):
+            try:
+                words = self.model.CORPORA[self.name]()
+                from operator import itemgetter
+
+                text = [w for w in words if len(w) > 2]
+                fd = FreqDist(tuple(text[i : i + 2]) for i in range(len(text) - 1))
+                vocab = FreqDist(text)
+                scored = [
+                    ((w1, w2), fd[(w1, w2)] ** 3 / (vocab[w1] * vocab[w2]))
+                    for w1, w2 in fd
+                ]
+                scored.sort(key=itemgetter(1), reverse=True)
+                self.model.collocations = list(map(itemgetter(0), scored))
+                self.model.queue.put(CORPUS_LOADED_EVENT)
+            except Exception as e:
+                print(e)
+                self.model.queue.put(ERROR_LOADING_CORPUS_EVENT)
+
+
+# def collocations():
+#    colloc_strings = [w1 + ' ' + w2 for w1, w2 in self._collocations[:num]]
+
+
+def app():
+    c = CollocationsView()
+    c.mainloop()
+
+
+if __name__ == "__main__":
+    app()
+
+__all__ = ["app"]

Backend/venv/lib/python3.12/site-packages/nltk/app/concordance_app.py

@@ -0,0 +1,709 @@
+# Natural Language Toolkit: Concordance Application
+#
+# Copyright (C) 2001-2025 NLTK Project
+# Author: Sumukh Ghodke <sghodke@csse.unimelb.edu.au>
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+
+import queue as q
+import re
+import threading
+from tkinter import (
+    END,
+    LEFT,
+    SUNKEN,
+    Button,
+    Entry,
+    Frame,
+    IntVar,
+    Label,
+    Menu,
+    OptionMenu,
+    Scrollbar,
+    StringVar,
+    Text,
+    Tk,
+)
+from tkinter.font import Font
+
+from nltk.corpus import (
+    alpino,
+    brown,
+    cess_cat,
+    cess_esp,
+    floresta,
+    indian,
+    mac_morpho,
+    nps_chat,
+    sinica_treebank,
+    treebank,
+)
+from nltk.draw.util import ShowText
+from nltk.util import in_idle
+
+WORD_OR_TAG = "[^/ ]+"
+BOUNDARY = r"\b"
+
+CORPUS_LOADED_EVENT = "<<CL_EVENT>>"
+SEARCH_TERMINATED_EVENT = "<<ST_EVENT>>"
+SEARCH_ERROR_EVENT = "<<SE_EVENT>>"
+ERROR_LOADING_CORPUS_EVENT = "<<ELC_EVENT>>"
+
+POLL_INTERVAL = 50
+
+# NB All corpora must be specified in a lambda expression so as not to be
+# loaded when the module is imported.
+
+_DEFAULT = "English: Brown Corpus (Humor, simplified)"
+_CORPORA = {
+    "Catalan: CESS-CAT Corpus (simplified)": lambda: cess_cat.tagged_sents(
+        tagset="universal"
+    ),
+    "English: Brown Corpus": lambda: brown.tagged_sents(),
+    "English: Brown Corpus (simplified)": lambda: brown.tagged_sents(
+        tagset="universal"
+    ),
+    "English: Brown Corpus (Press, simplified)": lambda: brown.tagged_sents(
+        categories=["news", "editorial", "reviews"], tagset="universal"
+    ),
+    "English: Brown Corpus (Religion, simplified)": lambda: brown.tagged_sents(
+        categories="religion", tagset="universal"
+    ),
+    "English: Brown Corpus (Learned, simplified)": lambda: brown.tagged_sents(
+        categories="learned", tagset="universal"
+    ),
+    "English: Brown Corpus (Science Fiction, simplified)": lambda: brown.tagged_sents(
+        categories="science_fiction", tagset="universal"
+    ),
+    "English: Brown Corpus (Romance, simplified)": lambda: brown.tagged_sents(
+        categories="romance", tagset="universal"
+    ),
+    "English: Brown Corpus (Humor, simplified)": lambda: brown.tagged_sents(
+        categories="humor", tagset="universal"
+    ),
+    "English: NPS Chat Corpus": lambda: nps_chat.tagged_posts(),
+    "English: NPS Chat Corpus (simplified)": lambda: nps_chat.tagged_posts(
+        tagset="universal"
+    ),
+    "English: Wall Street Journal Corpus": lambda: treebank.tagged_sents(),
+    "English: Wall Street Journal Corpus (simplified)": lambda: treebank.tagged_sents(
+        tagset="universal"
+    ),
+    "Chinese: Sinica Corpus": lambda: sinica_treebank.tagged_sents(),
+    "Chinese: Sinica Corpus (simplified)": lambda: sinica_treebank.tagged_sents(
+        tagset="universal"
+    ),
+    "Dutch: Alpino Corpus": lambda: alpino.tagged_sents(),
+    "Dutch: Alpino Corpus (simplified)": lambda: alpino.tagged_sents(
+        tagset="universal"
+    ),
+    "Hindi: Indian Languages Corpus": lambda: indian.tagged_sents(files="hindi.pos"),
+    "Hindi: Indian Languages Corpus (simplified)": lambda: indian.tagged_sents(
+        files="hindi.pos", tagset="universal"
+    ),
+    "Portuguese: Floresta Corpus (Portugal)": lambda: floresta.tagged_sents(),
+    "Portuguese: Floresta Corpus (Portugal, simplified)": lambda: floresta.tagged_sents(
+        tagset="universal"
+    ),
+    "Portuguese: MAC-MORPHO Corpus (Brazil)": lambda: mac_morpho.tagged_sents(),
+    "Portuguese: MAC-MORPHO Corpus (Brazil, simplified)": lambda: mac_morpho.tagged_sents(
+        tagset="universal"
+    ),
+    "Spanish: CESS-ESP Corpus (simplified)": lambda: cess_esp.tagged_sents(
+        tagset="universal"
+    ),
+}
+
+
+class ConcordanceSearchView:
+    _BACKGROUND_COLOUR = "#FFF"  # white
+
+    # Colour of highlighted results
+    _HIGHLIGHT_WORD_COLOUR = "#F00"  # red
+    _HIGHLIGHT_WORD_TAG = "HL_WRD_TAG"
+
+    _HIGHLIGHT_LABEL_COLOUR = "#C0C0C0"  # dark grey
+    _HIGHLIGHT_LABEL_TAG = "HL_LBL_TAG"
+
+    # Percentage of text left of the scrollbar position
+    _FRACTION_LEFT_TEXT = 0.30
+
+    def __init__(self):
+        self.queue = q.Queue()
+        self.model = ConcordanceSearchModel(self.queue)
+        self.top = Tk()
+        self._init_top(self.top)
+        self._init_menubar()
+        self._init_widgets(self.top)
+        self.load_corpus(self.model.DEFAULT_CORPUS)
+        self.after = self.top.after(POLL_INTERVAL, self._poll)
+
+    def _init_top(self, top):
+        top.geometry("950x680+50+50")
+        top.title("NLTK Concordance Search")
+        top.bind("<Control-q>", self.destroy)
+        top.protocol("WM_DELETE_WINDOW", self.destroy)
+        top.minsize(950, 680)
+
+    def _init_widgets(self, parent):
+        self.main_frame = Frame(
+            parent, dict(background=self._BACKGROUND_COLOUR, padx=1, pady=1, border=1)
+        )
+        self._init_corpus_select(self.main_frame)
+        self._init_query_box(self.main_frame)
+        self._init_results_box(self.main_frame)
+        self._init_paging(self.main_frame)
+        self._init_status(self.main_frame)
+        self.main_frame.pack(fill="both", expand=True)
+
+    def _init_menubar(self):
+        self._result_size = IntVar(self.top)
+        self._cntx_bf_len = IntVar(self.top)
+        self._cntx_af_len = IntVar(self.top)
+        menubar = Menu(self.top)
+
+        filemenu = Menu(menubar, tearoff=0, borderwidth=0)
+        filemenu.add_command(
+            label="Exit", underline=1, command=self.destroy, accelerator="Ctrl-q"
+        )
+        menubar.add_cascade(label="File", underline=0, menu=filemenu)
+
+        editmenu = Menu(menubar, tearoff=0)
+        rescntmenu = Menu(editmenu, tearoff=0)
+        rescntmenu.add_radiobutton(
+            label="20",
+            variable=self._result_size,
+            underline=0,
+            value=20,
+            command=self.set_result_size,
+        )
+        rescntmenu.add_radiobutton(
+            label="50",
+            variable=self._result_size,
+            underline=0,
+            value=50,
+            command=self.set_result_size,
+        )
+        rescntmenu.add_radiobutton(
+            label="100",
+            variable=self._result_size,
+            underline=0,
+            value=100,
+            command=self.set_result_size,
+        )
+        rescntmenu.invoke(1)
+        editmenu.add_cascade(label="Result Count", underline=0, menu=rescntmenu)
+
+        cntxmenu = Menu(editmenu, tearoff=0)
+        cntxbfmenu = Menu(cntxmenu, tearoff=0)
+        cntxbfmenu.add_radiobutton(
+            label="60 characters",
+            variable=self._cntx_bf_len,
+            underline=0,
+            value=60,
+            command=self.set_cntx_bf_len,
+        )
+        cntxbfmenu.add_radiobutton(
+            label="80 characters",
+            variable=self._cntx_bf_len,
+            underline=0,
+            value=80,
+            command=self.set_cntx_bf_len,
+        )
+        cntxbfmenu.add_radiobutton(
+            label="100 characters",
+            variable=self._cntx_bf_len,
+            underline=0,
+            value=100,
+            command=self.set_cntx_bf_len,
+        )
+        cntxbfmenu.invoke(1)
+        cntxmenu.add_cascade(label="Before", underline=0, menu=cntxbfmenu)
+
+        cntxafmenu = Menu(cntxmenu, tearoff=0)
+        cntxafmenu.add_radiobutton(
+            label="70 characters",
+            variable=self._cntx_af_len,
+            underline=0,
+            value=70,
+            command=self.set_cntx_af_len,
+        )
+        cntxafmenu.add_radiobutton(
+            label="90 characters",
+            variable=self._cntx_af_len,
+            underline=0,
+            value=90,
+            command=self.set_cntx_af_len,
+        )
+        cntxafmenu.add_radiobutton(
+            label="110 characters",
+            variable=self._cntx_af_len,
+            underline=0,
+            value=110,
+            command=self.set_cntx_af_len,
+        )
+        cntxafmenu.invoke(1)
+        cntxmenu.add_cascade(label="After", underline=0, menu=cntxafmenu)
+
+        editmenu.add_cascade(label="Context", underline=0, menu=cntxmenu)
+
+        menubar.add_cascade(label="Edit", underline=0, menu=editmenu)
+
+        self.top.config(menu=menubar)
+
+    def set_result_size(self, **kwargs):
+        self.model.result_count = self._result_size.get()
+
+    def set_cntx_af_len(self, **kwargs):
+        self._char_after = self._cntx_af_len.get()
+
+    def set_cntx_bf_len(self, **kwargs):
+        self._char_before = self._cntx_bf_len.get()
+
+    def _init_corpus_select(self, parent):
+        innerframe = Frame(parent, background=self._BACKGROUND_COLOUR)
+        self.var = StringVar(innerframe)
+        self.var.set(self.model.DEFAULT_CORPUS)
+        Label(
+            innerframe,
+            justify=LEFT,
+            text=" Corpus: ",
+            background=self._BACKGROUND_COLOUR,
+            padx=2,
+            pady=1,
+            border=0,
+        ).pack(side="left")
+
+        other_corpora = list(self.model.CORPORA.keys()).remove(
+            self.model.DEFAULT_CORPUS
+        )
+        om = OptionMenu(
+            innerframe,
+            self.var,
+            self.model.DEFAULT_CORPUS,
+            command=self.corpus_selected,
+            *self.model.non_default_corpora()
+        )
+        om["borderwidth"] = 0
+        om["highlightthickness"] = 1
+        om.pack(side="left")
+        innerframe.pack(side="top", fill="x", anchor="n")
+
+    def _init_status(self, parent):
+        self.status = Label(
+            parent,
+            justify=LEFT,
+            relief=SUNKEN,
+            background=self._BACKGROUND_COLOUR,
+            border=0,
+            padx=1,
+            pady=0,
+        )
+        self.status.pack(side="top", anchor="sw")
+
+    def _init_query_box(self, parent):
+        innerframe = Frame(parent, background=self._BACKGROUND_COLOUR)
+        another = Frame(innerframe, background=self._BACKGROUND_COLOUR)
+        self.query_box = Entry(another, width=60)
+        self.query_box.pack(side="left", fill="x", pady=25, anchor="center")
+        self.search_button = Button(
+            another,
+            text="Search",
+            command=self.search,
+            borderwidth=1,
+            highlightthickness=1,
+        )
+        self.search_button.pack(side="left", fill="x", pady=25, anchor="center")
+        self.query_box.bind("<KeyPress-Return>", self.search_enter_keypress_handler)
+        another.pack()
+        innerframe.pack(side="top", fill="x", anchor="n")
+
+    def search_enter_keypress_handler(self, *event):
+        self.search()
+
+    def _init_results_box(self, parent):
+        innerframe = Frame(parent)
+        i1 = Frame(innerframe)
+        i2 = Frame(innerframe)
+        vscrollbar = Scrollbar(i1, borderwidth=1)
+        hscrollbar = Scrollbar(i2, borderwidth=1, orient="horiz")
+        self.results_box = Text(
+            i1,
+            font=Font(family="courier", size="16"),
+            state="disabled",
+            borderwidth=1,
+            yscrollcommand=vscrollbar.set,
+            xscrollcommand=hscrollbar.set,
+            wrap="none",
+            width="40",
+            height="20",
+            exportselection=1,
+        )
+        self.results_box.pack(side="left", fill="both", expand=True)
+        self.results_box.tag_config(
+            self._HIGHLIGHT_WORD_TAG, foreground=self._HIGHLIGHT_WORD_COLOUR
+        )
+        self.results_box.tag_config(
+            self._HIGHLIGHT_LABEL_TAG, foreground=self._HIGHLIGHT_LABEL_COLOUR
+        )
+        vscrollbar.pack(side="left", fill="y", anchor="e")
+        vscrollbar.config(command=self.results_box.yview)
+        hscrollbar.pack(side="left", fill="x", expand=True, anchor="w")
+        hscrollbar.config(command=self.results_box.xview)
+        # there is no other way of avoiding the overlap of scrollbars while using pack layout manager!!!
+        Label(i2, text="   ", background=self._BACKGROUND_COLOUR).pack(
+            side="left", anchor="e"
+        )
+        i1.pack(side="top", fill="both", expand=True, anchor="n")
+        i2.pack(side="bottom", fill="x", anchor="s")
+        innerframe.pack(side="top", fill="both", expand=True)
+
+    def _init_paging(self, parent):
+        innerframe = Frame(parent, background=self._BACKGROUND_COLOUR)
+        self.prev = prev = Button(
+            innerframe,
+            text="Previous",
+            command=self.previous,
+            width="10",
+            borderwidth=1,
+            highlightthickness=1,
+            state="disabled",
+        )
+        prev.pack(side="left", anchor="center")
+        self.next = next = Button(
+            innerframe,
+            text="Next",
+            command=self.__next__,
+            width="10",
+            borderwidth=1,
+            highlightthickness=1,
+            state="disabled",
+        )
+        next.pack(side="right", anchor="center")
+        innerframe.pack(side="top", fill="y")
+        self.current_page = 0
+
+    def previous(self):
+        self.clear_results_box()
+        self.freeze_editable()
+        self.model.prev(self.current_page - 1)
+
+    def __next__(self):
+        self.clear_results_box()
+        self.freeze_editable()
+        self.model.next(self.current_page + 1)
+
+    def about(self, *e):
+        ABOUT = "NLTK Concordance Search Demo\n"
+        TITLE = "About: NLTK Concordance Search Demo"
+        try:
+            from tkinter.messagebox import Message
+
+            Message(message=ABOUT, title=TITLE, parent=self.main_frame).show()
+        except:
+            ShowText(self.top, TITLE, ABOUT)
+
+    def _bind_event_handlers(self):
+        self.top.bind(CORPUS_LOADED_EVENT, self.handle_corpus_loaded)
+        self.top.bind(SEARCH_TERMINATED_EVENT, self.handle_search_terminated)
+        self.top.bind(SEARCH_ERROR_EVENT, self.handle_search_error)
+        self.top.bind(ERROR_LOADING_CORPUS_EVENT, self.handle_error_loading_corpus)
+
+    def _poll(self):
+        try:
+            event = self.queue.get(block=False)
+        except q.Empty:
+            pass
+        else:
+            if event == CORPUS_LOADED_EVENT:
+                self.handle_corpus_loaded(event)
+            elif event == SEARCH_TERMINATED_EVENT:
+                self.handle_search_terminated(event)
+            elif event == SEARCH_ERROR_EVENT:
+                self.handle_search_error(event)
+            elif event == ERROR_LOADING_CORPUS_EVENT:
+                self.handle_error_loading_corpus(event)
+        self.after = self.top.after(POLL_INTERVAL, self._poll)
+
+    def handle_error_loading_corpus(self, event):
+        self.status["text"] = "Error in loading " + self.var.get()
+        self.unfreeze_editable()
+        self.clear_all()
+        self.freeze_editable()
+
+    def handle_corpus_loaded(self, event):
+        self.status["text"] = self.var.get() + " is loaded"
+        self.unfreeze_editable()
+        self.clear_all()
+        self.query_box.focus_set()
+
+    def handle_search_terminated(self, event):
+        # todo: refactor the model such that it is less state sensitive
+        results = self.model.get_results()
+        self.write_results(results)
+        self.status["text"] = ""
+        if len(results) == 0:
+            self.status["text"] = "No results found for " + self.model.query
+        else:
+            self.current_page = self.model.last_requested_page
+        self.unfreeze_editable()
+        self.results_box.xview_moveto(self._FRACTION_LEFT_TEXT)
+
+    def handle_search_error(self, event):
+        self.status["text"] = "Error in query " + self.model.query
+        self.unfreeze_editable()
+
+    def corpus_selected(self, *args):
+        new_selection = self.var.get()
+        self.load_corpus(new_selection)
+
+    def load_corpus(self, selection):
+        if self.model.selected_corpus != selection:
+            self.status["text"] = "Loading " + selection + "..."
+            self.freeze_editable()
+            self.model.load_corpus(selection)
+
+    def search(self):
+        self.current_page = 0
+        self.clear_results_box()
+        self.model.reset_results()
+        query = self.query_box.get()
+        if len(query.strip()) == 0:
+            return
+        self.status["text"] = "Searching for " + query
+        self.freeze_editable()
+        self.model.search(query, self.current_page + 1)
+
+    def write_results(self, results):
+        self.results_box["state"] = "normal"
+        row = 1
+        for each in results:
+            sent, pos1, pos2 = each[0].strip(), each[1], each[2]
+            if len(sent) != 0:
+                if pos1 < self._char_before:
+                    sent, pos1, pos2 = self.pad(sent, pos1, pos2)
+                sentence = sent[pos1 - self._char_before : pos1 + self._char_after]
+                if not row == len(results):
+                    sentence += "\n"
+                self.results_box.insert(str(row) + ".0", sentence)
+                word_markers, label_markers = self.words_and_labels(sent, pos1, pos2)
+                for marker in word_markers:
+                    self.results_box.tag_add(
+                        self._HIGHLIGHT_WORD_TAG,
+                        str(row) + "." + str(marker[0]),
+                        str(row) + "." + str(marker[1]),
+                    )
+                for marker in label_markers:
+                    self.results_box.tag_add(
+                        self._HIGHLIGHT_LABEL_TAG,
+                        str(row) + "." + str(marker[0]),
+                        str(row) + "." + str(marker[1]),
+                    )
+                row += 1
+        self.results_box["state"] = "disabled"
+
+    def words_and_labels(self, sentence, pos1, pos2):
+        search_exp = sentence[pos1:pos2]
+        words, labels = [], []
+        labeled_words = search_exp.split(" ")
+        index = 0
+        for each in labeled_words:
+            if each == "":
+                index += 1
+            else:
+                word, label = each.split("/")
+                words.append(
+                    (self._char_before + index, self._char_before + index + len(word))
+                )
+                index += len(word) + 1
+                labels.append(
+                    (self._char_before + index, self._char_before + index + len(label))
+                )
+                index += len(label)
+            index += 1
+        return words, labels
+
+    def pad(self, sent, hstart, hend):
+        if hstart >= self._char_before:
+            return sent, hstart, hend
+        d = self._char_before - hstart
+        sent = "".join([" "] * d) + sent
+        return sent, hstart + d, hend + d
+
+    def destroy(self, *e):
+        if self.top is None:
+            return
+        self.top.after_cancel(self.after)
+        self.top.destroy()
+        self.top = None
+
+    def clear_all(self):
+        self.query_box.delete(0, END)
+        self.model.reset_query()
+        self.clear_results_box()
+
+    def clear_results_box(self):
+        self.results_box["state"] = "normal"
+        self.results_box.delete("1.0", END)
+        self.results_box["state"] = "disabled"
+
+    def freeze_editable(self):
+        self.query_box["state"] = "disabled"
+        self.search_button["state"] = "disabled"
+        self.prev["state"] = "disabled"
+        self.next["state"] = "disabled"
+
+    def unfreeze_editable(self):
+        self.query_box["state"] = "normal"
+        self.search_button["state"] = "normal"
+        self.set_paging_button_states()
+
+    def set_paging_button_states(self):
+        if self.current_page == 0 or self.current_page == 1:
+            self.prev["state"] = "disabled"
+        else:
+            self.prev["state"] = "normal"
+        if self.model.has_more_pages(self.current_page):
+            self.next["state"] = "normal"
+        else:
+            self.next["state"] = "disabled"
+
+    def fire_event(self, event):
+        # Firing an event so that rendering of widgets happen in the mainloop thread
+        self.top.event_generate(event, when="tail")
+
+    def mainloop(self, *args, **kwargs):
+        if in_idle():
+            return
+        self.top.mainloop(*args, **kwargs)
+
+
+class ConcordanceSearchModel:
+    def __init__(self, queue):
+        self.queue = queue
+        self.CORPORA = _CORPORA
+        self.DEFAULT_CORPUS = _DEFAULT
+        self.selected_corpus = None
+        self.reset_query()
+        self.reset_results()
+        self.result_count = None
+        self.last_sent_searched = 0
+
+    def non_default_corpora(self):
+        copy = []
+        copy.extend(list(self.CORPORA.keys()))
+        copy.remove(self.DEFAULT_CORPUS)
+        copy.sort()
+        return copy
+
+    def load_corpus(self, name):
+        self.selected_corpus = name
+        self.tagged_sents = []
+        runner_thread = self.LoadCorpus(name, self)
+        runner_thread.start()
+
+    def search(self, query, page):
+        self.query = query
+        self.last_requested_page = page
+        self.SearchCorpus(self, page, self.result_count).start()
+
+    def next(self, page):
+        self.last_requested_page = page
+        if len(self.results) < page:
+            self.search(self.query, page)
+        else:
+            self.queue.put(SEARCH_TERMINATED_EVENT)
+
+    def prev(self, page):
+        self.last_requested_page = page
+        self.queue.put(SEARCH_TERMINATED_EVENT)
+
+    def reset_results(self):
+        self.last_sent_searched = 0
+        self.results = []
+        self.last_page = None
+
+    def reset_query(self):
+        self.query = None
+
+    def set_results(self, page, resultset):
+        self.results.insert(page - 1, resultset)
+
+    def get_results(self):
+        return self.results[self.last_requested_page - 1]
+
+    def has_more_pages(self, page):
+        if self.results == [] or self.results[0] == []:
+            return False
+        if self.last_page is None:
+            return True
+        return page < self.last_page
+
+    class LoadCorpus(threading.Thread):
+        def __init__(self, name, model):
+            threading.Thread.__init__(self)
+            self.model, self.name = model, name
+
+        def run(self):
+            try:
+                ts = self.model.CORPORA[self.name]()
+                self.model.tagged_sents = [
+                    " ".join(w + "/" + t for (w, t) in sent) for sent in ts
+                ]
+                self.model.queue.put(CORPUS_LOADED_EVENT)
+            except Exception as e:
+                print(e)
+                self.model.queue.put(ERROR_LOADING_CORPUS_EVENT)
+
+    class SearchCorpus(threading.Thread):
+        def __init__(self, model, page, count):
+            self.model, self.count, self.page = model, count, page
+            threading.Thread.__init__(self)
+
+        def run(self):
+            q = self.processed_query()
+            sent_pos, i, sent_count = [], 0, 0
+            for sent in self.model.tagged_sents[self.model.last_sent_searched :]:
+                try:
+                    m = re.search(q, sent)
+                except re.error:
+                    self.model.reset_results()
+                    self.model.queue.put(SEARCH_ERROR_EVENT)
+                    return
+                if m:
+                    sent_pos.append((sent, m.start(), m.end()))
+                    i += 1
+                    if i > self.count:
+                        self.model.last_sent_searched += sent_count - 1
+                        break
+                sent_count += 1
+            if self.count >= len(sent_pos):
+                self.model.last_sent_searched += sent_count - 1
+                self.model.last_page = self.page
+                self.model.set_results(self.page, sent_pos)
+            else:
+                self.model.set_results(self.page, sent_pos[:-1])
+            self.model.queue.put(SEARCH_TERMINATED_EVENT)
+
+        def processed_query(self):
+            new = []
+            for term in self.model.query.split():
+                term = re.sub(r"\.", r"[^/ ]", term)
+                if re.match("[A-Z]+$", term):
+                    new.append(BOUNDARY + WORD_OR_TAG + "/" + term + BOUNDARY)
+                elif "/" in term:
+                    new.append(BOUNDARY + term + BOUNDARY)
+                else:
+                    new.append(BOUNDARY + term + "/" + WORD_OR_TAG + BOUNDARY)
+            return " ".join(new)
+
+
+def app():
+    d = ConcordanceSearchView()
+    d.mainloop()
+
+
+if __name__ == "__main__":
+    app()
+
+__all__ = ["app"]

Backend/venv/lib/python3.12/site-packages/nltk/app/nemo_app.py

@@ -0,0 +1,163 @@
+# Finding (and Replacing) Nemo, Version 1.1, Aristide Grange 2006/06/06
+# https://aspn.activestate.com/ASPN/Cookbook/Python/Recipe/496783
+
+"""
+Finding (and Replacing) Nemo
+
+Instant Regular Expressions
+Created by Aristide Grange
+"""
+import itertools
+import re
+from tkinter import SEL_FIRST, SEL_LAST, Frame, Label, PhotoImage, Scrollbar, Text, Tk
+
+windowTitle = "Finding (and Replacing) Nemo"
+initialFind = r"n(.*?)e(.*?)m(.*?)o"
+initialRepl = r"M\1A\2K\3I"
+initialText = """\
+Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
+Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat.
+Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.
+Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.
+"""
+images = {
+    "FIND": "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",
+    "find": "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",
+    "REPL": "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",
+    "repl": "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",
+}
+colors = ["#FF7B39", "#80F121"]
+emphColors = ["#DAFC33", "#F42548"]
+fieldParams = {
+    "height": 3,
+    "width": 70,
+    "font": ("monaco", 14),
+    "highlightthickness": 0,
+    "borderwidth": 0,
+    "background": "white",
+}
+textParams = {
+    "bg": "#F7E0D4",
+    "fg": "#2321F1",
+    "highlightthickness": 0,
+    "width": 1,
+    "height": 10,
+    "font": ("verdana", 16),
+    "wrap": "word",
+}
+
+
+class Zone:
+    def __init__(self, image, initialField, initialText):
+        frm = Frame(root)
+        frm.config(background="white")
+        self.image = PhotoImage(format="gif", data=images[image.upper()])
+        self.imageDimmed = PhotoImage(format="gif", data=images[image])
+        self.img = Label(frm)
+        self.img.config(borderwidth=0)
+        self.img.pack(side="left")
+        self.fld = Text(frm, **fieldParams)
+        self.initScrollText(frm, self.fld, initialField)
+        frm = Frame(root)
+        self.txt = Text(frm, **textParams)
+        self.initScrollText(frm, self.txt, initialText)
+        for i in range(2):
+            self.txt.tag_config(colors[i], background=colors[i])
+            self.txt.tag_config("emph" + colors[i], foreground=emphColors[i])
+
+    def initScrollText(self, frm, txt, contents):
+        scl = Scrollbar(frm)
+        scl.config(command=txt.yview)
+        scl.pack(side="right", fill="y")
+        txt.pack(side="left", expand=True, fill="x")
+        txt.config(yscrollcommand=scl.set)
+        txt.insert("1.0", contents)
+        frm.pack(fill="x")
+        Frame(height=2, bd=1, relief="ridge").pack(fill="x")
+
+    def refresh(self):
+        self.colorCycle = itertools.cycle(colors)
+        try:
+            self.substitute()
+            self.img.config(image=self.image)
+        except re.error:
+            self.img.config(image=self.imageDimmed)
+
+
+class FindZone(Zone):
+    def addTags(self, m):
+        color = next(self.colorCycle)
+        self.txt.tag_add(color, "1.0+%sc" % m.start(), "1.0+%sc" % m.end())
+        try:
+            self.txt.tag_add(
+                "emph" + color, "1.0+%sc" % m.start("emph"), "1.0+%sc" % m.end("emph")
+            )
+        except:
+            pass
+
+    def substitute(self, *args):
+        for color in colors:
+            self.txt.tag_remove(color, "1.0", "end")
+            self.txt.tag_remove("emph" + color, "1.0", "end")
+        self.rex = re.compile("")  # default value in case of malformed regexp
+        self.rex = re.compile(self.fld.get("1.0", "end")[:-1], re.MULTILINE)
+        try:
+            re.compile("(?P<emph>%s)" % self.fld.get(SEL_FIRST, SEL_LAST))
+            self.rexSel = re.compile(
+                "%s(?P<emph>%s)%s"
+                % (
+                    self.fld.get("1.0", SEL_FIRST),
+                    self.fld.get(SEL_FIRST, SEL_LAST),
+                    self.fld.get(SEL_LAST, "end")[:-1],
+                ),
+                re.MULTILINE,
+            )
+        except:
+            self.rexSel = self.rex
+        self.rexSel.sub(self.addTags, self.txt.get("1.0", "end"))
+
+
+class ReplaceZone(Zone):
+    def addTags(self, m):
+        s = sz.rex.sub(self.repl, m.group())
+        self.txt.delete(
+            "1.0+%sc" % (m.start() + self.diff), "1.0+%sc" % (m.end() + self.diff)
+        )
+        self.txt.insert("1.0+%sc" % (m.start() + self.diff), s, next(self.colorCycle))
+        self.diff += len(s) - (m.end() - m.start())
+
+    def substitute(self):
+        self.txt.delete("1.0", "end")
+        self.txt.insert("1.0", sz.txt.get("1.0", "end")[:-1])
+        self.diff = 0
+        self.repl = rex0.sub(r"\\g<\1>", self.fld.get("1.0", "end")[:-1])
+        sz.rex.sub(self.addTags, sz.txt.get("1.0", "end")[:-1])
+
+
+def launchRefresh(_):
+    sz.fld.after_idle(sz.refresh)
+    rz.fld.after_idle(rz.refresh)
+
+
+def app():
+    global root, sz, rz, rex0
+    root = Tk()
+    root.resizable(height=False, width=True)
+    root.title(windowTitle)
+    root.minsize(width=250, height=0)
+    sz = FindZone("find", initialFind, initialText)
+    sz.fld.bind("<Button-1>", launchRefresh)
+    sz.fld.bind("<ButtonRelease-1>", launchRefresh)
+    sz.fld.bind("<B1-Motion>", launchRefresh)
+    sz.rexSel = re.compile("")
+    rz = ReplaceZone("repl", initialRepl, "")
+    rex0 = re.compile(r"(?<!\\)\\([0-9]+)")
+    root.bind_all("<Key>", launchRefresh)
+    launchRefresh(None)
+    root.mainloop()
+
+
+if __name__ == "__main__":
+    app()
+
+__all__ = ["app"]

Backend/venv/lib/python3.12/site-packages/nltk/app/srparser_app.py

@@ -0,0 +1,937 @@
+# Natural Language Toolkit: Shift-Reduce Parser Application
+#
+# Copyright (C) 2001-2025 NLTK Project
+# Author: Edward Loper <edloper@gmail.com>
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+
+"""
+A graphical tool for exploring the shift-reduce parser.
+
+The shift-reduce parser maintains a stack, which records the structure
+of the portion of the text that has been parsed.  The stack is
+initially empty.  Its contents are shown on the left side of the main
+canvas.
+
+On the right side of the main canvas is the remaining text.  This is
+the portion of the text which has not yet been considered by the
+parser.
+
+The parser builds up a tree structure for the text using two
+operations:
+
+  - "shift" moves the first token from the remaining text to the top
+    of the stack.  In the demo, the top of the stack is its right-hand
+    side.
+  - "reduce" uses a grammar production to combine the rightmost stack
+    elements into a single tree token.
+
+You can control the parser's operation by using the "shift" and
+"reduce" buttons; or you can use the "step" button to let the parser
+automatically decide which operation to apply.  The parser uses the
+following rules to decide which operation to apply:
+
+  - Only shift if no reductions are available.
+  - If multiple reductions are available, then apply the reduction
+    whose CFG production is listed earliest in the grammar.
+
+The "reduce" button applies the reduction whose CFG production is
+listed earliest in the grammar.  There are two ways to manually choose
+which reduction to apply:
+
+  - Click on a CFG production from the list of available reductions,
+    on the left side of the main window.  The reduction based on that
+    production will be applied to the top of the stack.
+  - Click on one of the stack elements.  A popup window will appear,
+    containing all available reductions.  Select one, and it will be
+    applied to the top of the stack.
+
+Note that reductions can only be applied to the top of the stack.
+
+Keyboard Shortcuts::
+      [Space]\t Perform the next shift or reduce operation
+      [s]\t Perform a shift operation
+      [r]\t Perform a reduction operation
+      [Ctrl-z]\t Undo most recent operation
+      [Delete]\t Reset the parser
+      [g]\t Show/hide available production list
+      [Ctrl-a]\t Toggle animations
+      [h]\t Help
+      [Ctrl-p]\t Print
+      [q]\t Quit
+
+"""
+
+from tkinter import Button, Frame, IntVar, Label, Listbox, Menu, Scrollbar, Tk
+from tkinter.font import Font
+
+from nltk.draw import CFGEditor, TreeSegmentWidget, tree_to_treesegment
+from nltk.draw.util import CanvasFrame, EntryDialog, ShowText, TextWidget
+from nltk.parse import SteppingShiftReduceParser
+from nltk.tree import Tree
+from nltk.util import in_idle
+
+"""
+Possible future improvements:
+  - button/window to change and/or select text.  Just pop up a window
+    with an entry, and let them modify the text; and then retokenize
+    it?  Maybe give a warning if it contains tokens whose types are
+    not in the grammar.
+  - button/window to change and/or select grammar.  Select from
+    several alternative grammars?  Or actually change the grammar?  If
+    the later, then I'd want to define nltk.draw.cfg, which would be
+    responsible for that.
+"""
+
+
+class ShiftReduceApp:
+    """
+    A graphical tool for exploring the shift-reduce parser.  The tool
+    displays the parser's stack and the remaining text, and allows the
+    user to control the parser's operation.  In particular, the user
+    can shift tokens onto the stack, and can perform reductions on the
+    top elements of the stack.  A "step" button simply steps through
+    the parsing process, performing the operations that
+    ``nltk.parse.ShiftReduceParser`` would use.
+    """
+
+    def __init__(self, grammar, sent, trace=0):
+        self._sent = sent
+        self._parser = SteppingShiftReduceParser(grammar, trace)
+
+        # Set up the main window.
+        self._top = Tk()
+        self._top.title("Shift Reduce Parser Application")
+
+        # Animations.  animating_lock is a lock to prevent the demo
+        # from performing new operations while it's animating.
+        self._animating_lock = 0
+        self._animate = IntVar(self._top)
+        self._animate.set(10)  # = medium
+
+        # The user can hide the grammar.
+        self._show_grammar = IntVar(self._top)
+        self._show_grammar.set(1)
+
+        # Initialize fonts.
+        self._init_fonts(self._top)
+
+        # Set up key bindings.
+        self._init_bindings()
+
+        # Create the basic frames.
+        self._init_menubar(self._top)
+        self._init_buttons(self._top)
+        self._init_feedback(self._top)
+        self._init_grammar(self._top)
+        self._init_canvas(self._top)
+
+        # A popup menu for reducing.
+        self._reduce_menu = Menu(self._canvas, tearoff=0)
+
+        # Reset the demo, and set the feedback frame to empty.
+        self.reset()
+        self._lastoper1["text"] = ""
+
+    #########################################
+    ##  Initialization Helpers
+    #########################################
+
+    def _init_fonts(self, root):
+        # See: <http://www.astro.washington.edu/owen/ROTKFolklore.html>
+        self._sysfont = Font(font=Button()["font"])
+        root.option_add("*Font", self._sysfont)
+
+        # TWhat's our font size (default=same as sysfont)
+        self._size = IntVar(root)
+        self._size.set(self._sysfont.cget("size"))
+
+        self._boldfont = Font(family="helvetica", weight="bold", size=self._size.get())
+        self._font = Font(family="helvetica", size=self._size.get())
+
+    def _init_grammar(self, parent):
+        # Grammar view.
+        self._prodframe = listframe = Frame(parent)
+        self._prodframe.pack(fill="both", side="left", padx=2)
+        self._prodlist_label = Label(
+            self._prodframe, font=self._boldfont, text="Available Reductions"
+        )
+        self._prodlist_label.pack()
+        self._prodlist = Listbox(
+            self._prodframe,
+            selectmode="single",
+            relief="groove",
+            background="white",
+            foreground="#909090",
+            font=self._font,
+            selectforeground="#004040",
+            selectbackground="#c0f0c0",
+        )
+
+        self._prodlist.pack(side="right", fill="both", expand=1)
+
+        self._productions = list(self._parser.grammar().productions())
+        for production in self._productions:
+            self._prodlist.insert("end", (" %s" % production))
+        self._prodlist.config(height=min(len(self._productions), 25))
+
+        # Add a scrollbar if there are more than 25 productions.
+        if 1:  # len(self._productions) > 25:
+            listscroll = Scrollbar(self._prodframe, orient="vertical")
+            self._prodlist.config(yscrollcommand=listscroll.set)
+            listscroll.config(command=self._prodlist.yview)
+            listscroll.pack(side="left", fill="y")
+
+        # If they select a production, apply it.
+        self._prodlist.bind("<<ListboxSelect>>", self._prodlist_select)
+
+        # When they hover over a production, highlight it.
+        self._hover = -1
+        self._prodlist.bind("<Motion>", self._highlight_hover)
+        self._prodlist.bind("<Leave>", self._clear_hover)
+
+    def _init_bindings(self):
+        # Quit
+        self._top.bind("<Control-q>", self.destroy)
+        self._top.bind("<Control-x>", self.destroy)
+        self._top.bind("<Alt-q>", self.destroy)
+        self._top.bind("<Alt-x>", self.destroy)
+
+        # Ops (step, shift, reduce, undo)
+        self._top.bind("<space>", self.step)
+        self._top.bind("<s>", self.shift)
+        self._top.bind("<Alt-s>", self.shift)
+        self._top.bind("<Control-s>", self.shift)
+        self._top.bind("<r>", self.reduce)
+        self._top.bind("<Alt-r>", self.reduce)
+        self._top.bind("<Control-r>", self.reduce)
+        self._top.bind("<Delete>", self.reset)
+        self._top.bind("<u>", self.undo)
+        self._top.bind("<Alt-u>", self.undo)
+        self._top.bind("<Control-u>", self.undo)
+        self._top.bind("<Control-z>", self.undo)
+        self._top.bind("<BackSpace>", self.undo)
+
+        # Misc
+        self._top.bind("<Control-p>", self.postscript)
+        self._top.bind("<Control-h>", self.help)
+        self._top.bind("<F1>", self.help)
+        self._top.bind("<Control-g>", self.edit_grammar)
+        self._top.bind("<Control-t>", self.edit_sentence)
+
+        # Animation speed control
+        self._top.bind("-", lambda e, a=self._animate: a.set(20))
+        self._top.bind("=", lambda e, a=self._animate: a.set(10))
+        self._top.bind("+", lambda e, a=self._animate: a.set(4))
+
+    def _init_buttons(self, parent):
+        # Set up the frames.
+        self._buttonframe = buttonframe = Frame(parent)
+        buttonframe.pack(fill="none", side="bottom")
+        Button(
+            buttonframe,
+            text="Step",
+            background="#90c0d0",
+            foreground="black",
+            command=self.step,
+        ).pack(side="left")
+        Button(
+            buttonframe,
+            text="Shift",
+            underline=0,
+            background="#90f090",
+            foreground="black",
+            command=self.shift,
+        ).pack(side="left")
+        Button(
+            buttonframe,
+            text="Reduce",
+            underline=0,
+            background="#90f090",
+            foreground="black",
+            command=self.reduce,
+        ).pack(side="left")
+        Button(
+            buttonframe,
+            text="Undo",
+            underline=0,
+            background="#f0a0a0",
+            foreground="black",
+            command=self.undo,
+        ).pack(side="left")
+
+    def _init_menubar(self, parent):
+        menubar = Menu(parent)
+
+        filemenu = Menu(menubar, tearoff=0)
+        filemenu.add_command(
+            label="Reset Parser", underline=0, command=self.reset, accelerator="Del"
+        )
+        filemenu.add_command(
+            label="Print to Postscript",
+            underline=0,
+            command=self.postscript,
+            accelerator="Ctrl-p",
+        )
+        filemenu.add_command(
+            label="Exit", underline=1, command=self.destroy, accelerator="Ctrl-x"
+        )
+        menubar.add_cascade(label="File", underline=0, menu=filemenu)
+
+        editmenu = Menu(menubar, tearoff=0)
+        editmenu.add_command(
+            label="Edit Grammar",
+            underline=5,
+            command=self.edit_grammar,
+            accelerator="Ctrl-g",
+        )
+        editmenu.add_command(
+            label="Edit Text",
+            underline=5,
+            command=self.edit_sentence,
+            accelerator="Ctrl-t",
+        )
+        menubar.add_cascade(label="Edit", underline=0, menu=editmenu)
+
+        rulemenu = Menu(menubar, tearoff=0)
+        rulemenu.add_command(
+            label="Step", underline=1, command=self.step, accelerator="Space"
+        )
+        rulemenu.add_separator()
+        rulemenu.add_command(
+            label="Shift", underline=0, command=self.shift, accelerator="Ctrl-s"
+        )
+        rulemenu.add_command(
+            label="Reduce", underline=0, command=self.reduce, accelerator="Ctrl-r"
+        )
+        rulemenu.add_separator()
+        rulemenu.add_command(
+            label="Undo", underline=0, command=self.undo, accelerator="Ctrl-u"
+        )
+        menubar.add_cascade(label="Apply", underline=0, menu=rulemenu)
+
+        viewmenu = Menu(menubar, tearoff=0)
+        viewmenu.add_checkbutton(
+            label="Show Grammar",
+            underline=0,
+            variable=self._show_grammar,
+            command=self._toggle_grammar,
+        )
+        viewmenu.add_separator()
+        viewmenu.add_radiobutton(
+            label="Tiny",
+            variable=self._size,
+            underline=0,
+            value=10,
+            command=self.resize,
+        )
+        viewmenu.add_radiobutton(
+            label="Small",
+            variable=self._size,
+            underline=0,
+            value=12,
+            command=self.resize,
+        )
+        viewmenu.add_radiobutton(
+            label="Medium",
+            variable=self._size,
+            underline=0,
+            value=14,
+            command=self.resize,
+        )
+        viewmenu.add_radiobutton(
+            label="Large",
+            variable=self._size,
+            underline=0,
+            value=18,
+            command=self.resize,
+        )
+        viewmenu.add_radiobutton(
+            label="Huge",
+            variable=self._size,
+            underline=0,
+            value=24,
+            command=self.resize,
+        )
+        menubar.add_cascade(label="View", underline=0, menu=viewmenu)
+
+        animatemenu = Menu(menubar, tearoff=0)
+        animatemenu.add_radiobutton(
+            label="No Animation", underline=0, variable=self._animate, value=0
+        )
+        animatemenu.add_radiobutton(
+            label="Slow Animation",
+            underline=0,
+            variable=self._animate,
+            value=20,
+            accelerator="-",
+        )
+        animatemenu.add_radiobutton(
+            label="Normal Animation",
+            underline=0,
+            variable=self._animate,
+            value=10,
+            accelerator="=",
+        )
+        animatemenu.add_radiobutton(
+            label="Fast Animation",
+            underline=0,
+            variable=self._animate,
+            value=4,
+            accelerator="+",
+        )
+        menubar.add_cascade(label="Animate", underline=1, menu=animatemenu)
+
+        helpmenu = Menu(menubar, tearoff=0)
+        helpmenu.add_command(label="About", underline=0, command=self.about)
+        helpmenu.add_command(
+            label="Instructions", underline=0, command=self.help, accelerator="F1"
+        )
+        menubar.add_cascade(label="Help", underline=0, menu=helpmenu)
+
+        parent.config(menu=menubar)
+
+    def _init_feedback(self, parent):
+        self._feedbackframe = feedbackframe = Frame(parent)
+        feedbackframe.pack(fill="x", side="bottom", padx=3, pady=3)
+        self._lastoper_label = Label(
+            feedbackframe, text="Last Operation:", font=self._font
+        )
+        self._lastoper_label.pack(side="left")
+        lastoperframe = Frame(feedbackframe, relief="sunken", border=1)
+        lastoperframe.pack(fill="x", side="right", expand=1, padx=5)
+        self._lastoper1 = Label(
+            lastoperframe, foreground="#007070", background="#f0f0f0", font=self._font
+        )
+        self._lastoper2 = Label(
+            lastoperframe,
+            anchor="w",
+            width=30,
+            foreground="#004040",
+            background="#f0f0f0",
+            font=self._font,
+        )
+        self._lastoper1.pack(side="left")
+        self._lastoper2.pack(side="left", fill="x", expand=1)
+
+    def _init_canvas(self, parent):
+        self._cframe = CanvasFrame(
+            parent,
+            background="white",
+            width=525,
+            closeenough=10,
+            border=2,
+            relief="sunken",
+        )
+        self._cframe.pack(expand=1, fill="both", side="top", pady=2)
+        canvas = self._canvas = self._cframe.canvas()
+
+        self._stackwidgets = []
+        self._rtextwidgets = []
+        self._titlebar = canvas.create_rectangle(
+            0, 0, 0, 0, fill="#c0f0f0", outline="black"
+        )
+        self._exprline = canvas.create_line(0, 0, 0, 0, dash=".")
+        self._stacktop = canvas.create_line(0, 0, 0, 0, fill="#408080")
+        size = self._size.get() + 4
+        self._stacklabel = TextWidget(
+            canvas, "Stack", color="#004040", font=self._boldfont
+        )
+        self._rtextlabel = TextWidget(
+            canvas, "Remaining Text", color="#004040", font=self._boldfont
+        )
+        self._cframe.add_widget(self._stacklabel)
+        self._cframe.add_widget(self._rtextlabel)
+
+    #########################################
+    ##  Main draw procedure
+    #########################################
+
+    def _redraw(self):
+        scrollregion = self._canvas["scrollregion"].split()
+        (cx1, cy1, cx2, cy2) = (int(c) for c in scrollregion)
+
+        # Delete the old stack & rtext widgets.
+        for stackwidget in self._stackwidgets:
+            self._cframe.destroy_widget(stackwidget)
+        self._stackwidgets = []
+        for rtextwidget in self._rtextwidgets:
+            self._cframe.destroy_widget(rtextwidget)
+        self._rtextwidgets = []
+
+        # Position the titlebar & exprline
+        (x1, y1, x2, y2) = self._stacklabel.bbox()
+        y = y2 - y1 + 10
+        self._canvas.coords(self._titlebar, -5000, 0, 5000, y - 4)
+        self._canvas.coords(self._exprline, 0, y * 2 - 10, 5000, y * 2 - 10)
+
+        # Position the titlebar labels..
+        (x1, y1, x2, y2) = self._stacklabel.bbox()
+        self._stacklabel.move(5 - x1, 3 - y1)
+        (x1, y1, x2, y2) = self._rtextlabel.bbox()
+        self._rtextlabel.move(cx2 - x2 - 5, 3 - y1)
+
+        # Draw the stack.
+        stackx = 5
+        for tok in self._parser.stack():
+            if isinstance(tok, Tree):
+                attribs = {
+                    "tree_color": "#4080a0",
+                    "tree_width": 2,
+                    "node_font": self._boldfont,
+                    "node_color": "#006060",
+                    "leaf_color": "#006060",
+                    "leaf_font": self._font,
+                }
+                widget = tree_to_treesegment(self._canvas, tok, **attribs)
+                widget.label()["color"] = "#000000"
+            else:
+                widget = TextWidget(self._canvas, tok, color="#000000", font=self._font)
+            widget.bind_click(self._popup_reduce)
+            self._stackwidgets.append(widget)
+            self._cframe.add_widget(widget, stackx, y)
+            stackx = widget.bbox()[2] + 10
+
+        # Draw the remaining text.
+        rtextwidth = 0
+        for tok in self._parser.remaining_text():
+            widget = TextWidget(self._canvas, tok, color="#000000", font=self._font)
+            self._rtextwidgets.append(widget)
+            self._cframe.add_widget(widget, rtextwidth, y)
+            rtextwidth = widget.bbox()[2] + 4
+
+        # Allow enough room to shift the next token (for animations)
+        if len(self._rtextwidgets) > 0:
+            stackx += self._rtextwidgets[0].width()
+
+        # Move the remaining text to the correct location (keep it
+        # right-justified, when possible); and move the remaining text
+        # label, if necessary.
+        stackx = max(stackx, self._stacklabel.width() + 25)
+        rlabelwidth = self._rtextlabel.width() + 10
+        if stackx >= cx2 - max(rtextwidth, rlabelwidth):
+            cx2 = stackx + max(rtextwidth, rlabelwidth)
+        for rtextwidget in self._rtextwidgets:
+            rtextwidget.move(4 + cx2 - rtextwidth, 0)
+        self._rtextlabel.move(cx2 - self._rtextlabel.bbox()[2] - 5, 0)
+
+        midx = (stackx + cx2 - max(rtextwidth, rlabelwidth)) / 2
+        self._canvas.coords(self._stacktop, midx, 0, midx, 5000)
+        (x1, y1, x2, y2) = self._stacklabel.bbox()
+
+        # Set up binding to allow them to shift a token by dragging it.
+        if len(self._rtextwidgets) > 0:
+
+            def drag_shift(widget, midx=midx, self=self):
+                if widget.bbox()[0] < midx:
+                    self.shift()
+                else:
+                    self._redraw()
+
+            self._rtextwidgets[0].bind_drag(drag_shift)
+            self._rtextwidgets[0].bind_click(self.shift)
+
+        # Draw the stack top.
+        self._highlight_productions()
+
+    def _draw_stack_top(self, widget):
+        # hack..
+        midx = widget.bbox()[2] + 50
+        self._canvas.coords(self._stacktop, midx, 0, midx, 5000)
+
+    def _highlight_productions(self):
+        # Highlight the productions that can be reduced.
+        self._prodlist.selection_clear(0, "end")
+        for prod in self._parser.reducible_productions():
+            index = self._productions.index(prod)
+            self._prodlist.selection_set(index)
+
+    #########################################
+    ##  Button Callbacks
+    #########################################
+
+    def destroy(self, *e):
+        if self._top is None:
+            return
+        self._top.destroy()
+        self._top = None
+
+    def reset(self, *e):
+        self._parser.initialize(self._sent)
+        self._lastoper1["text"] = "Reset App"
+        self._lastoper2["text"] = ""
+        self._redraw()
+
+    def step(self, *e):
+        if self.reduce():
+            return True
+        elif self.shift():
+            return True
+        else:
+            if list(self._parser.parses()):
+                self._lastoper1["text"] = "Finished:"
+                self._lastoper2["text"] = "Success"
+            else:
+                self._lastoper1["text"] = "Finished:"
+                self._lastoper2["text"] = "Failure"
+
+    def shift(self, *e):
+        if self._animating_lock:
+            return
+        if self._parser.shift():
+            tok = self._parser.stack()[-1]
+            self._lastoper1["text"] = "Shift:"
+            self._lastoper2["text"] = "%r" % tok
+            if self._animate.get():
+                self._animate_shift()
+            else:
+                self._redraw()
+            return True
+        return False
+
+    def reduce(self, *e):
+        if self._animating_lock:
+            return
+        production = self._parser.reduce()
+        if production:
+            self._lastoper1["text"] = "Reduce:"
+            self._lastoper2["text"] = "%s" % production
+            if self._animate.get():
+                self._animate_reduce()
+            else:
+                self._redraw()
+        return production
+
+    def undo(self, *e):
+        if self._animating_lock:
+            return
+        if self._parser.undo():
+            self._redraw()
+
+    def postscript(self, *e):
+        self._cframe.print_to_file()
+
+    def mainloop(self, *args, **kwargs):
+        """
+        Enter the Tkinter mainloop.  This function must be called if
+        this demo is created from a non-interactive program (e.g.
+        from a secript); otherwise, the demo will close as soon as
+        the script completes.
+        """
+        if in_idle():
+            return
+        self._top.mainloop(*args, **kwargs)
+
+    #########################################
+    ##  Menubar callbacks
+    #########################################
+
+    def resize(self, size=None):
+        if size is not None:
+            self._size.set(size)
+        size = self._size.get()
+        self._font.configure(size=-(abs(size)))
+        self._boldfont.configure(size=-(abs(size)))
+        self._sysfont.configure(size=-(abs(size)))
+
+        # self._stacklabel['font'] = ('helvetica', -size-4, 'bold')
+        # self._rtextlabel['font'] = ('helvetica', -size-4, 'bold')
+        # self._lastoper_label['font'] = ('helvetica', -size)
+        # self._lastoper1['font'] = ('helvetica', -size)
+        # self._lastoper2['font'] = ('helvetica', -size)
+        # self._prodlist['font'] = ('helvetica', -size)
+        # self._prodlist_label['font'] = ('helvetica', -size-2, 'bold')
+        self._redraw()
+
+    def help(self, *e):
+        # The default font's not very legible; try using 'fixed' instead.
+        try:
+            ShowText(
+                self._top,
+                "Help: Shift-Reduce Parser Application",
+                (__doc__ or "").strip(),
+                width=75,
+                font="fixed",
+            )
+        except:
+            ShowText(
+                self._top,
+                "Help: Shift-Reduce Parser Application",
+                (__doc__ or "").strip(),
+                width=75,
+            )
+
+    def about(self, *e):
+        ABOUT = "NLTK Shift-Reduce Parser Application\n" + "Written by Edward Loper"
+        TITLE = "About: Shift-Reduce Parser Application"
+        try:
+            from tkinter.messagebox import Message
+
+            Message(message=ABOUT, title=TITLE).show()
+        except:
+            ShowText(self._top, TITLE, ABOUT)
+
+    def edit_grammar(self, *e):
+        CFGEditor(self._top, self._parser.grammar(), self.set_grammar)
+
+    def set_grammar(self, grammar):
+        self._parser.set_grammar(grammar)
+        self._productions = list(grammar.productions())
+        self._prodlist.delete(0, "end")
+        for production in self._productions:
+            self._prodlist.insert("end", (" %s" % production))
+
+    def edit_sentence(self, *e):
+        sentence = " ".join(self._sent)
+        title = "Edit Text"
+        instr = "Enter a new sentence to parse."
+        EntryDialog(self._top, sentence, instr, self.set_sentence, title)
+
+    def set_sentence(self, sent):
+        self._sent = sent.split()  # [XX] use tagged?
+        self.reset()
+
+    #########################################
+    ##  Reduce Production Selection
+    #########################################
+
+    def _toggle_grammar(self, *e):
+        if self._show_grammar.get():
+            self._prodframe.pack(
+                fill="both", side="left", padx=2, after=self._feedbackframe
+            )
+            self._lastoper1["text"] = "Show Grammar"
+        else:
+            self._prodframe.pack_forget()
+            self._lastoper1["text"] = "Hide Grammar"
+        self._lastoper2["text"] = ""
+
+    def _prodlist_select(self, event):
+        selection = self._prodlist.curselection()
+        if len(selection) != 1:
+            return
+        index = int(selection[0])
+        production = self._parser.reduce(self._productions[index])
+        if production:
+            self._lastoper1["text"] = "Reduce:"
+            self._lastoper2["text"] = "%s" % production
+            if self._animate.get():
+                self._animate_reduce()
+            else:
+                self._redraw()
+        else:
+            # Reset the production selections.
+            self._prodlist.selection_clear(0, "end")
+            for prod in self._parser.reducible_productions():
+                index = self._productions.index(prod)
+                self._prodlist.selection_set(index)
+
+    def _popup_reduce(self, widget):
+        # Remove old commands.
+        productions = self._parser.reducible_productions()
+        if len(productions) == 0:
+            return
+
+        self._reduce_menu.delete(0, "end")
+        for production in productions:
+            self._reduce_menu.add_command(label=str(production), command=self.reduce)
+        self._reduce_menu.post(
+            self._canvas.winfo_pointerx(), self._canvas.winfo_pointery()
+        )
+
+    #########################################
+    ##  Animations
+    #########################################
+
+    def _animate_shift(self):
+        # What widget are we shifting?
+        widget = self._rtextwidgets[0]
+
+        # Where are we shifting from & to?
+        right = widget.bbox()[0]
+        if len(self._stackwidgets) == 0:
+            left = 5
+        else:
+            left = self._stackwidgets[-1].bbox()[2] + 10
+
+        # Start animating.
+        dt = self._animate.get()
+        dx = (left - right) * 1.0 / dt
+        self._animate_shift_frame(dt, widget, dx)
+
+    def _animate_shift_frame(self, frame, widget, dx):
+        if frame > 0:
+            self._animating_lock = 1
+            widget.move(dx, 0)
+            self._top.after(10, self._animate_shift_frame, frame - 1, widget, dx)
+        else:
+            # but: stacktop??
+
+            # Shift the widget to the stack.
+            del self._rtextwidgets[0]
+            self._stackwidgets.append(widget)
+            self._animating_lock = 0
+
+            # Display the available productions.
+            self._draw_stack_top(widget)
+            self._highlight_productions()
+
+    def _animate_reduce(self):
+        # What widgets are we shifting?
+        numwidgets = len(self._parser.stack()[-1])  # number of children
+        widgets = self._stackwidgets[-numwidgets:]
+
+        # How far are we moving?
+        if isinstance(widgets[0], TreeSegmentWidget):
+            ydist = 15 + widgets[0].label().height()
+        else:
+            ydist = 15 + widgets[0].height()
+
+        # Start animating.
+        dt = self._animate.get()
+        dy = ydist * 2.0 / dt
+        self._animate_reduce_frame(dt / 2, widgets, dy)
+
+    def _animate_reduce_frame(self, frame, widgets, dy):
+        if frame > 0:
+            self._animating_lock = 1
+            for widget in widgets:
+                widget.move(0, dy)
+            self._top.after(10, self._animate_reduce_frame, frame - 1, widgets, dy)
+        else:
+            del self._stackwidgets[-len(widgets) :]
+            for widget in widgets:
+                self._cframe.remove_widget(widget)
+            tok = self._parser.stack()[-1]
+            if not isinstance(tok, Tree):
+                raise ValueError()
+            label = TextWidget(
+                self._canvas, str(tok.label()), color="#006060", font=self._boldfont
+            )
+            widget = TreeSegmentWidget(self._canvas, label, widgets, width=2)
+            (x1, y1, x2, y2) = self._stacklabel.bbox()
+            y = y2 - y1 + 10
+            if not self._stackwidgets:
+                x = 5
+            else:
+                x = self._stackwidgets[-1].bbox()[2] + 10
+            self._cframe.add_widget(widget, x, y)
+            self._stackwidgets.append(widget)
+
+            # Display the available productions.
+            self._draw_stack_top(widget)
+            self._highlight_productions()
+
+            #             # Delete the old widgets..
+            #             del self._stackwidgets[-len(widgets):]
+            #             for widget in widgets:
+            #                 self._cframe.destroy_widget(widget)
+            #
+            #             # Make a new one.
+            #             tok = self._parser.stack()[-1]
+            #             if isinstance(tok, Tree):
+            #                 attribs = {'tree_color': '#4080a0', 'tree_width': 2,
+            #                            'node_font': bold, 'node_color': '#006060',
+            #                            'leaf_color': '#006060', 'leaf_font':self._font}
+            #                 widget = tree_to_treesegment(self._canvas, tok.type(),
+            #                                              **attribs)
+            #                 widget.node()['color'] = '#000000'
+            #             else:
+            #                 widget = TextWidget(self._canvas, tok.type(),
+            #                                     color='#000000', font=self._font)
+            #             widget.bind_click(self._popup_reduce)
+            #             (x1, y1, x2, y2) = self._stacklabel.bbox()
+            #             y = y2-y1+10
+            #             if not self._stackwidgets: x = 5
+            #             else: x = self._stackwidgets[-1].bbox()[2] + 10
+            #             self._cframe.add_widget(widget, x, y)
+            #             self._stackwidgets.append(widget)
+
+            # self._redraw()
+            self._animating_lock = 0
+
+    #########################################
+    ##  Hovering.
+    #########################################
+
+    def _highlight_hover(self, event):
+        # What production are we hovering over?
+        index = self._prodlist.nearest(event.y)
+        if self._hover == index:
+            return
+
+        # Clear any previous hover highlighting.
+        self._clear_hover()
+
+        # If the production corresponds to an available reduction,
+        # highlight the stack.
+        selection = [int(s) for s in self._prodlist.curselection()]
+        if index in selection:
+            rhslen = len(self._productions[index].rhs())
+            for stackwidget in self._stackwidgets[-rhslen:]:
+                if isinstance(stackwidget, TreeSegmentWidget):
+                    stackwidget.label()["color"] = "#00a000"
+                else:
+                    stackwidget["color"] = "#00a000"
+
+        # Remember what production we're hovering over.
+        self._hover = index
+
+    def _clear_hover(self, *event):
+        # Clear any previous hover highlighting.
+        if self._hover == -1:
+            return
+        self._hover = -1
+        for stackwidget in self._stackwidgets:
+            if isinstance(stackwidget, TreeSegmentWidget):
+                stackwidget.label()["color"] = "black"
+            else:
+                stackwidget["color"] = "black"
+
+
+def app():
+    """
+    Create a shift reduce parser app, using a simple grammar and
+    text.
+    """
+
+    from nltk.grammar import CFG, Nonterminal, Production
+
+    nonterminals = "S VP NP PP P N Name V Det"
+    (S, VP, NP, PP, P, N, Name, V, Det) = (Nonterminal(s) for s in nonterminals.split())
+
+    productions = (
+        # Syntactic Productions
+        Production(S, [NP, VP]),
+        Production(NP, [Det, N]),
+        Production(NP, [NP, PP]),
+        Production(VP, [VP, PP]),
+        Production(VP, [V, NP, PP]),
+        Production(VP, [V, NP]),
+        Production(PP, [P, NP]),
+        # Lexical Productions
+        Production(NP, ["I"]),
+        Production(Det, ["the"]),
+        Production(Det, ["a"]),
+        Production(N, ["man"]),
+        Production(V, ["saw"]),
+        Production(P, ["in"]),
+        Production(P, ["with"]),
+        Production(N, ["park"]),
+        Production(N, ["dog"]),
+        Production(N, ["statue"]),
+        Production(Det, ["my"]),
+    )
+
+    grammar = CFG(S, productions)
+
+    # tokenize the sentence
+    sent = "my dog saw a man in the park with a statue".split()
+
+    ShiftReduceApp(grammar, sent).mainloop()
+
+
+if __name__ == "__main__":
+    app()
+
+__all__ = ["app"]

Backend/venv/lib/python3.12/site-packages/nltk/app/wordfreq_app.py

@@ -0,0 +1,36 @@
+# Natural Language Toolkit: Wordfreq Application
+#
+# Copyright (C) 2001-2025 NLTK Project
+# Author: Sumukh Ghodke <sghodke@csse.unimelb.edu.au>
+# URL: <https://www.nltk.org/>
+# For license information, see LICENSE.TXT
+
+from matplotlib import pylab
+
+from nltk.corpus import gutenberg
+from nltk.text import Text
+
+
+def plot_word_freq_dist(text):
+    fd = text.vocab()
+
+    samples = [item for item, _ in fd.most_common(50)]
+    values = [fd[sample] for sample in samples]
+    values = [sum(values[: i + 1]) * 100.0 / fd.N() for i in range(len(values))]
+    pylab.title(text.name)
+    pylab.xlabel("Samples")
+    pylab.ylabel("Cumulative Percentage")
+    pylab.plot(values)
+    pylab.xticks(range(len(samples)), [str(s) for s in samples], rotation=90)
+    pylab.show()
+
+
+def app():
+    t1 = Text(gutenberg.words("melville-moby_dick.txt"))
+    plot_word_freq_dist(t1)
+
+
+if __name__ == "__main__":
+    app()
+
+__all__ = ["app"]